← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Pro (14c) · 36 GB · 4bit · 2026-05-22
Performance
16k
tokens
432.6
PP tok/s
34.5
TG tok/s
37869
TTFT (ms)
15.6
Peak mem (GB)
Hardware
Chip M3 Pro (14c)
Memory 36 GB
GPU Cores 14
Software
oMLX v0.3.9
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 426.6 40.8 14.3 GB view
4k 446.3 37.9 14.9 GB view
8k 456.8 38.0 15.1 GB view
16k 432.6 34.5 15.6 GB current
32k 385.2 27.7 16.5 GB view
64k 310.0 15.6 18.7 GB view